@inproceedings{singh-etal-2023-viphy,
title = "{VIPHY}: Probing {``}Visible{''} Physical Commonsense Knowledge",
author = "Singh, Shikhar and
Qasemi, Ehsan and
Chen, Muhao",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.473",
doi = "10.18653/v1/2023.findings-emnlp.473",
pages = "7113--7128",
abstract = "Vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge. In this work, we evaluate VLMs{'} ability to acquire {``}visible{''} physical knowledge {--} the information that is easily accessible from images of static scenes, particularly along the dimensions of object color, size, and space. We build an automatic pipeline to derive a comprehensive knowledge resource for calibrating and probing these models. Our results indicate a severe gap between model and human performance across all three dimensions. Furthermore, we demonstrate that a caption pretrained LM significantly outperforms VLMs on both size and spatial tasks {--} highlighting that despite sufficient access to ground language with visual modality, they struggle to retain such knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2023-viphy">
<titleInfo>
<title>VIPHY: Probing “Visible” Physical Commonsense Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Qasemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge. In this work, we evaluate VLMs’ ability to acquire “visible” physical knowledge – the information that is easily accessible from images of static scenes, particularly along the dimensions of object color, size, and space. We build an automatic pipeline to derive a comprehensive knowledge resource for calibrating and probing these models. Our results indicate a severe gap between model and human performance across all three dimensions. Furthermore, we demonstrate that a caption pretrained LM significantly outperforms VLMs on both size and spatial tasks – highlighting that despite sufficient access to ground language with visual modality, they struggle to retain such knowledge.</abstract>
<identifier type="citekey">singh-etal-2023-viphy</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.473</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.473</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7113</start>
<end>7128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VIPHY: Probing “Visible” Physical Commonsense Knowledge
%A Singh, Shikhar
%A Qasemi, Ehsan
%A Chen, Muhao
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F singh-etal-2023-viphy
%X Vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge. In this work, we evaluate VLMs’ ability to acquire “visible” physical knowledge – the information that is easily accessible from images of static scenes, particularly along the dimensions of object color, size, and space. We build an automatic pipeline to derive a comprehensive knowledge resource for calibrating and probing these models. Our results indicate a severe gap between model and human performance across all three dimensions. Furthermore, we demonstrate that a caption pretrained LM significantly outperforms VLMs on both size and spatial tasks – highlighting that despite sufficient access to ground language with visual modality, they struggle to retain such knowledge.
%R 10.18653/v1/2023.findings-emnlp.473
%U https://aclanthology.org/2023.findings-emnlp.473
%U https://doi.org/10.18653/v1/2023.findings-emnlp.473
%P 7113-7128
Markdown (Informal)
[VIPHY: Probing “Visible” Physical Commonsense Knowledge](https://aclanthology.org/2023.findings-emnlp.473) (Singh et al., Findings 2023)
ACL